Co-matching: Combating Noisy Labels by Augmentation Anchoring
This addresses noisy label issues in deep learning, which is an incremental improvement over existing methods.
The paper tackles the problem of deep learning with noisy labels by proposing Co-matching, which uses augmentation anchoring to balance consistency and divergence between two networks, achieving results comparable to state-of-the-art methods on three benchmark datasets.
Deep learning with noisy labels is challenging as deep neural networks have the high capacity to memorize the noisy labels. In this paper, we propose a learning algorithm called Co-matching, which balances the consistency and divergence between two networks by augmentation anchoring. Specifically, we have one network generate anchoring label from its prediction on a weakly-augmented image. Meanwhile, we force its peer network, taking the strongly-augmented version of the same image as input, to generate prediction close to the anchoring label. We then update two networks simultaneously by selecting small-loss instances to minimize both unsupervised matching loss (i.e., measure the consistency of the two networks) and supervised classification loss (i.e. measure the classification performance). Besides, the unsupervised matching loss makes our method not heavily rely on noisy labels, which prevents memorization of noisy labels. Experiments on three benchmark datasets demonstrate that Co-matching achieves results comparable to the state-of-the-art methods.